Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the mutation profile is covered. The description adds genuinely new behavioral context: the undo is single-step and scoped to four specific tools, and it deliberately leaves non-assistant (in-app) changes alone. It does not say whether undo itself is reversible or what happens when no undable change exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero redundancy. The core behavior and the list of affected tools come first, and the scoping caveat follows immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the agent gets no structured signal about the response, and the description does not say what an undo returns or what the failure mode is when there's nothing to undo. Given that annotations cover the destructive profile and parameters are fully documented, this is a small remaining gap rather than a blocking one.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — project_id ('as vedutum_list_projects returns it') and the language enum are both documented in the schema. The description adds nothing about either parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Restores ... to the state before the last change') and resource (a project), and names the exact four sibling tools whose effects it reverts (vedutum_furnish_rooms, vedutum_set_design, vedutum_add_solar, vedutum_set_site_address). An agent can distinguish this from any other sibling without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'One step' and 'changes made in the app are not touched' give clear applicability conditions and an implicit exclusion: it only undoes the immediately preceding assistant-driven change, not repeated or manual edits. It stops short of stating what to do if the last change wasn't one of the four named tools, or what happens when nothing is undoable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.